Theory and Applications of Models of Computation

Volume 3959 of the series Lecture Notes in Computer Science pp 408-420

On the Foundations of Universal Sequence Prediction

  • Marcus HutterAffiliated withIDSIA

* Final gross prices may vary according to local VAT.

Get Access


Solomonoff completed the Bayesian framework by providing a rigorous, unique, formal, and universal choice for the model class and the prior. We discuss in breadth how and in which sense universal (non-i.i.d.) sequence prediction solves various (philosophical) problems of traditional Bayesian sequence prediction. We show that Solomonoff’s model possesses many desirable properties: Fast convergence and strong bounds, and in contrast to most classical continuous prior densities has no zero p(oste)rior problem, i.e. can confirm universal hypotheses, is reparametrization and regrouping invariant, and avoids the old-evidence and updating problem. It even performs well (actually better) in non-computable environments.